Papers by Phillip Ströbel
Nunc profana tractemus. Detecting Code-Switching in a Large Corpus of 16th Century Letters (2022.lrec-1)
Copied to clipboard
Martin Volk, Lukas Fischer, Patricia Scheurer, Bernard Silvan Schroffenegger, Raphael Schwitter, Phillip Ströbel, Benjamin Suter
| Challenge: | a corpus of 16th century letters from and to the Zurich reformer Heinrich Bullinger has been preserved . a recent study investigated code-switching in these 8600 letters . |
| Approach: | They investigate the automatic detection of code-switching in a 16th century letter exchange . they use a popular language identifier to bootstrap a word-based language classifier . |
| Outcome: | The proposed language classifier bootstraps with a popular identifier on a small training corpus of 150 sentences per language. |